Explainable AI for B2B Credit Risk Assessment
Designing transparent, audit-ready AI credit decisioning UX that eliminated the "black box" problem in B2B lending reducing decision appeals by 40% and achieving full EU AI Act compliance.
The Situation
The "Black Box" Problem in B2B Lending
AI Decisions Without Explanation
Our B2B lending platform used a sophisticated ML model for credit risk scoring. The model performed well statistically but created a UX crisis. SMB applicants received decisions like "Application Declined" with no explanation. Loan officers could not explain decisions to regulators or customers.
-
Unexplainable Decisions 35% of declined SMBs filed appeals all citing inability to understand the decision rationale.
-
Regulatory Exposure The EU AI Act and FCA guidelines require high-risk AI systems to provide human-readable decision explanations.
-
Loan Officer Paralysis Officers could not contextualise AI scores, leading to manual overrides based on gut feel undermining the model's value.
The Explainability Gap
"The model is right but I can't explain why to my customer. That's a problem." Loan Officer
The Task
Designing for Two Users: Applicants & Officers
I needed to bridge the explainability gap not by simplifying the model, but by designing a UX layer that translated complex AI outputs into human-understandable, actionable narratives for two very different user types.
The SMB Applicant
"I got declined but no one can tell me why. What do I need to fix to get approved next time?"
The Loan Officer
"I need to explain this AI decision to the customer and the regulator. Right now, I can't."
The "Glass Box" Strategy
Instead of hiding the AI, we narrate it. Every credit decision becomes a story: what the AI saw, what it weighted, and what the applicant can do next. Transparency as a feature, not an afterthought.
The Action
Research, Design, and Validation
1 Discovery & Research
- Ran 12 contextual interviews with loan officers to map their decision-making mental model
- Conducted appeal analysis on 200+ declined applications to identify the top 5 confusion triggers
- Ran an EU AI Act compliance audit with legal team to define minimum explainability requirements
- Benchmarked explainability UX patterns across Stripe, Experian, and Funding Circle
Top 5 Appeal Reasons
2 Key Design Decisions
Factor Contribution Chart
A horizontal bar chart showing the top 5 factors that influenced the AI decision with plain-English labels, not ML jargon.
Credit Health Roadmap
A 3-step improvement plan generated by AI showing exactly what the SMB needs to change and what score improvement to expect.
Officer Override Audit Trail
A structured override form requiring officers to document their reasoning creating a regulator-ready audit trail for every human intervention.
The Design
Explainability as a First-Class Feature
Applicant Decision Screen
-
Decision Summary Card Plain-English verdict with a confidence indicator (e.g., "Strong Decline 94% confidence") replacing technical score outputs.
-
Top Factors Panel Colour-coded factor contributions (red = negative, green = positive) with hover tooltips explaining each factor in plain language.
-
Credit Health Roadmap AI-generated improvement plan with projected score changes for each recommended action turning rejection into a growth path.
-
Request Human Review One-click escalation to a loan officer with a pre-populated context brief reducing officer prep time by 15 minutes per case.
AI Confidence: 94% · Reviewed: March 2025
Top Influencing Factors
The Result
Transparency Built Trust and Revenue
"For the first time, I can sit across from an SMB client, show them exactly why the AI scored them the way it did, and walk them through what to do next. That's a game changer for client trust."
Senior Loan Officer, B2B Lending Platform